Object Detection Demo¶
Welcome to the object detection inference walkthrough! This notebook will walk you step by step through the process of using a pre-trained model to detect objects in an image. Make sure to follow the installation instructions before you start.
Imports¶
In [5]:
import numpy as np
import os
import sys
import tensorflow as tf
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
print("Import ok!")
Env setup¶
In [6]:
# This is needed to display the images.
%matplotlib inline
Object detection imports¶
Here are the imports from the object detection module.
In [7]:
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
print("Import ok!")
Model preparation¶
Variables¶
Any model exported using the export_inference_graph.py tool can be loaded here simply by changing PATH_TO_CKPT to point to a new .pb file.
By default we use an "SSD with Mobilenet" model here. See the detection model zoo for a list of other models that can be run out-of-the-box with varying speeds and accuracies.
In [15]:
#CKPT = 'faster_rcnn_resnet101_coco_11_06_2017/frozen_inference_graph.pb' # TODO change with trained network
CKPT = 'output_inference_graph/frozen_inference_graph.pb'
PATH_TO_LABELS = 'label_map.pbtxt'
NUM_CLASSES = 14
Load a (frozen) Tensorflow model into memory.¶
In [16]:
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
print("Loaded ok!")
Loading label map¶
Label maps map indices to category names, so that when our convolution network predicts 5, we know that this corresponds to airplane. Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine
In [17]:
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
print(category_index)
Helper code¶
In [18]:
def load_image_into_numpy_array(image):
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 3)).astype(np.uint8)
Detection¶
In [19]:
from glob import glob
In [22]:
PATH_TO_TEST_IMAGES_DIR = 'test_images_bosch'
print(os.path.join(PATH_TO_TEST_IMAGES_DIR, '*.jpg'))
TEST_IMAGE_PATHS = glob(os.path.join(PATH_TO_TEST_IMAGES_DIR, '*.png')) # PNG OR JPG
#TEST_IMAGE_PATHS = glob(os.path.join(PATH_TO_TEST_IMAGES_DIR, '*.jpg'))
print("Length of test images:", len(TEST_IMAGE_PATHS))
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
In [23]:
import time
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
# Definite input and output Tensors for detection_graph
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
for image_path in TEST_IMAGE_PATHS:
image = Image.open(image_path)
# the array based representation of the image will be used later in order to prepare the
# result image with boxes and labels on it.
image_np = load_image_into_numpy_array(image)
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
time0 = time.time()
# Actual detection.
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: image_np_expanded})
time1 = time.time()
print("Time in milliseconds", (time1 - time0) * 1000)
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8)
plt.figure(figsize=IMAGE_SIZE)
plt.imshow(image_np)
plt.show()
